DOVA:基于协商的多智能体协作以实现自主研究自动化
DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation
AI总结:
DOVA通过协商优先的协作机制、混合协同推理和自适应多层思考,提升多源信息整合与复杂任务处理能力,降低推理成本并提高回答准确性。
摘要:
大型语言模型(LLM)代理在工具使用、推理和代码生成方面表现出色,但在处理需要多源整合、对抗验证和个性化交付的复杂研究任务时存在根本限制。本文提出DOVA(深度协调多功能代理),引入三个关键创新:(1)协商优先的协作机制,通过持续用户模型和实体感知对话上下文进行显式元推理;(2)混合协同推理,一种可组合的三阶段流水线,整合群体多样性、黑板透明度和迭代细化;(3)自适应多层级思考,一种六级token预算分配方案,可将简单任务的推理成本降低40-60%,同时保持深度推理能力。我们正式化了核心算法,展示了七个系统配置的架构消融研究,并分析了每个组件对回答置信度、源覆盖度和token效率的贡献。
英文摘要:
Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation, yet single-agent systems exhibit fundamental limitations when confronted with complex research tasks demanding multi-source synthesis, adversarial verification, and personalized delivery. We present DOVA (Deep Orchestrated Versatile Agent), a multi-agent platform introducing three key innovations: (1) deliberation-first orchestration, where explicit meta-reasoning precedes tool invocation, informed by a persistent user model and entity-aware conversation context; (2) hybrid collaborative reasoning, a composable three-phase pipeline unifying ensemble diversity, blackboard transparency, and iterative refinement; and (3) adaptive multi-tiered thinking, a six-level token-budget allocation scheme that reduces inference cost by 40-60% on simple tasks while preserving deep reasoning capacity. We formalize the core algorithms, present an architectural ablation study across seven system configurations, and analyze the contribution of each component to answer confidence, source coverage, and token efficiency.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。